© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 19032
    Prev
    Next
    INDEX
    Explanations

    names or proper nouns, particularly the name "Shaw."

    oai_token-act-pair · gpt-3.5-turbo

    the name "Shaw" and to a lesser extent "Chow" in a legal or news context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dL
    -0.80
     illeg
    -0.71
     inherit
    -0.70
     voc
    -0.68
    edit
    -0.66
    ype
    -0.65
     latex
    -0.64
     admins
    -0.63
    0000000
    -0.63
    ãĥīãĥ©ãĤ´ãĥ³
    -0.61
    POSITIVE LOGITS
     Shaw
    4.03
     Chow
    1.54
    shaw
    1.31
     Finch
    1.27
     Scully
    1.24
     Hutch
    1.19
     Shapiro
    1.14
     Hutchinson
    1.11
     Horowitz
    1.10
     Wilkinson
    1.07
    Activations Density 0.022%

    No Known Activations